Vladimir Lekić

Screen for Tissue-Specific Markers of Drug-Induced Phospholipidosis Using Mass Spectrometry Imaging

Christoph Hoffmann, Vladimir Lekić, Michael Becker, Manfred Claassen

Drug-induced phospholipidosis is a common side effect of the pharmacological treatment. Although mostly reversible, it can lead to deleterious consequences, including inflammation and fibrosis. While it can be readily detected in tissue biopsies or cell cultures, biomarkers that can be measured noninvasively …

de, cn (code pays fourni par la source)

Automotive radar and camera fusion using Generative Adversarial Networks

Vladimir Lekić, Zdenka Babić

de, ba (code pays fourni par la source)

Using GANs to Enable Semantic Segmentation of Ranging Sensor Data

Vladimir Lekić, Zdenka Babić

Ranging sensors, such as radar and lidar, onboard the vehicle are considered to be very robust under changing environmental conditions. Largely owing to this reputation, they have found broad applicability in driver assistance, and consequently in autonomous driving systems. On the other …

ba (code pays fourni par la source)

Neneta: Heterogeneous computing complex-valued neural network framework

Vladimir Lekić, Zdenka Babić

Due to increased demand for computational efficiency for the training, validation and testing of artificial neural networks, many open source software frameworks have emerged. Almost exclusively GPU programming model of choice in such software frameworks is CUDA. Symptomatic is also lack of …

ba (code pays fourni par la source)

Multiphase Tensor Level-Set Method for Segmentation of Natural Images

Vladimir Lekić, Zdenka Babić

ba (code pays fourni par la source)